Papers › NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik, Jonathan T. Barron, Ravi Ramamoorthi, Ren Ng
We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm represents a scene using a fully-connected (non-convolutional) deep network, whose input is a single continuous 5D coordinate (spatial location (x,y,z) and viewing direction (θ, ϕ)) and whose output is the volume density and view-dependent emitted radiance at that spatial location. We synthesize views by querying 5D coordinates along camera rays and use classic volume rendering techniques to project the output colors and densities into an image. Because volume rendering is naturally differentiable, the only input required to optimize our representation is a set of images with known camera poses. We describe how to effectively optimize neural radiance fields to render photorealistic novel views of scenes with complicated geometry and appearance, and demonstrate results that outperform prior work on neural rendering and view synthesis. View synthesis results are best viewed as videos, so we urge readers to view our supplementary video for convincing comparisons.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2003.08934")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2003.08934", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2003.08934")
Code
Syntology 56 code samples: 54 from 11 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 56: 44 ran (of which 0 constructed an object rather than computing a result; 23 with no instrument failure: 1 honoured, 1 violated, 21 with no contract checked; 21 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 16 where our contract draft was wrong; 5 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 12 samples from 1 repository, 9 ran (6 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 42 samples from 10 repositories, 33 ran (17 with no instrument failure; 16 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
No sample is linked to this paper from 9 of its repositories that Syntology harvested for other papers:
- bebeal/mipnerf-pytorch, community (archive-listed): harvested for another paper, listed under the repository
- computational-imaging/automatic-integration, community (archive-listed): harvested for another paper, listed under the repository
- facebookresearch/NSVF, community (archive-listed): harvested for another paper, listed under the repository
- glouppe/info8010-deep-learning, community (archive-listed): harvested for another paper, listed under the repository
- kakaobrain/NeRF-Factory, community (archive-listed): harvested for another paper, listed under the repository
- kwea123/nerf_pl, community (archive-listed): harvested for another paper, listed under the repository
- DavidLandup0/deepvision, community (archive-listed): harvested for 2 other papers, listed under the repository
- keras-team/keras-io, community (archive-listed): harvested for another paper, listed under the repository
- xiuyu0000/papers_with_examples, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 44 samples that ran have no recorded date.
37 repositories listed; official and paper-mentioned ones first.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
56 samples harvested: 44 ran (of which 0 constructed an object rather than computing a result; 23 with no instrument failure: 1 honoured, 1 violated, 21 with no contract checked; 21 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 6 of the 56 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 11 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. 2 samples are listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
census: 6 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket run_nerf.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only ·
ce716d3807564106 · report
fixture: signature fn:callable/0/?, chunk:int/0/int · returned function · level recorded 2026-09-22 9a8470533015ce8b · report
fixture: signature x:EagerTensor/4/float, y:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-25 7ee442908cd304b1 · report
fixture: signature basedir:str/0/str, half_res:bool/0/bool, testskip:int/0/int · returned tuple · level recorded 2026-09-25 e69746042397f344 · report
fixture: signature scene:str/0/str, basedir:str/0/str, testskip:int/0/int · returned tuple · level recorded 2026-09-25 census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket this sample: bucket 3 of 11, arg 1: rank 1, kind float, dtype float64 load_llff.py ran · violated contract fingerprinted MIT (permissive) ·
1d6f8390d799f055 · report
fixture: signature x:ndarray/1/float · returned ndarray · level recorded 2026-09-22 5dfee35860e399af · report
fixture: signature theta:float/0/float, phi:float/0/float, radius:float/0/float · returned EagerTensor · level recorded 2026-09-25 36f5de7a0aae4a9b · report
fixture: signature pts:ndarray/2/float, c2w:ndarray/2/float · returned ndarray · level recorded 2026-09-25 9b2cb1a88d84aec6 · report
fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-22 aa52acee18f54d38 · report
fixture: signature z:ndarray/1/float, up:ndarray/1/float, pos:ndarray/1/float · returned ndarray · level recorded 2026-09-22 bc8041fd2b31b089 · report
4c51a645589e581f · report
fixture: signature ds:Tensor/3/float, N_c:int/0/int, t_i_c_bin_edges:Tensor/3/float, t_i_c_gap:Tensor/3/float, os:Tensor/3/float · returned tuple · level recorded 2026-09-22 8974e4406c79c5bd · report
fixture: signature w_is_c:Tensor/3/float, N_f:int/0/int, t_is_c:Tensor/3/float, t_f:float/0/float, os:Tensor/3/float, ds:Tensor/3/float · returned tuple · level recorded 2026-09-22 bde1f23d239dd9ad · report
fixture: signature w_is_c:Tensor/3/float, N_f:int/0/int, t_is_c:Tensor/3/float, t_f:float/0/float, os:Tensor/3/float, ds:Tensor/3/float, r_ts_c:Tensor/4/float, N_d:int/0/int, d_std:float/0/float, t_n:float/0/float · returned tuple · level recorded 2026-09-22 97be931adba5c037 · report
fixture: signature r_ts:Tensor/4/float, camera_distance:float/0/float, scale:float/0/float, W_i:Tensor/4/float · returned Tensor · level recorded 2026-09-22 b7f46d0d6eb9f533 · report
fixture: signature r_ts:Tensor/4/float, ds:Tensor/3/float, chunk_size:int/0/int, F:callable/0/?, t_is:Tensor/3/float · returned tuple · level recorded 2026-09-22 f5a79b19662b118c · report
fixture: signature model:callable/0/?, batches:MockBatches/0/?, input:Tensor/4/float, device:device/0/? · returned tuple · level recorded 2026-09-22 census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket train_gon.py unverified MIT (permissive) ·
61e92f9d263cddc9 · report
1a19fbfcebd5f31a · report
fixture: signature tensor:Tensor/3/float · returned ndarray · level recorded 2026-09-22 c28b6ff0b012dc3a · report
fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-24 0bc6c9ee0b5176e3 · report
fixture: signature include_input_xyz:bool/0/bool, include_input_dir:bool/0/bool, num_encoding_fn_xyz:int/0/int, num_encoding_fn_dir:int/0/int · returned tuple · level recorded 2026-09-24 924ec325aa22bca1 · report
fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-24 429e689dec4629ec · report
fixture: signature img:ndarray/3/int, options:Options/0/? · returned ndarray · level recorded 2026-09-24 6bf9156e8a423ebc · report
fixture: signature height:int/0/int, width:int/0/int, focal_length:float/0/float, tfrom_cam2world:ArrayImpl/2/float · returned tuple · level recorded 2026-09-25 ede4a3a14cd0c5a7 · report
fixture: signature rng:ArrayImpl/2/int, model_coarse:callable/0/?, model_fine:callable/0/?, coarse_embedding:list/1/int, fine_embedding:list/1/int, config:Config/0/? · returned tuple · level recorded 2026-09-24 6781dae351c0e669 · report
fixture: signature tensor:ArrayImpl/2/float, f:callable/0/?, chunksize:int/0/int, use_vmap:bool/0/bool · returned ArrayImpl · level recorded 2026-09-25 0f7fe9f9700b5d37 · report
fixture: signature tensor:ArrayImpl/2/float, f:callable/0/?, chunksize:int/0/int, use_vmap:bool/0/bool, rng:ArrayImpl/1/int · returned tuple · level recorded 2026-09-25 88f06f0c72b003cf · report
fixture: signature tensor:Tensor/2/float, num_encoding_functions:int/0/int, include_input:bool/0/bool, log_sampling:bool/0/bool · returned Tensor · level recorded 2026-09-24 c3cd90a5ba1fb061 · report
fixture: signature torch_params:dict/0/?, model_name:str/0/str · returned dict · level recorded 2026-09-24 4cf87da067a5c9b0 · report
898a883c9cbd99f6 · report
527832def209c604 · report
d0c2ad169481a881 · report
9e4eb567d4c26168 · report
fixture: signature rays:Tensor/2/float, near:float/0/float, far:float/0/float, steps:int/0/int, lindisp:bool/0/bool, perturb:float/0/float · returned tuple · level recorded 2026-09-22 29bf7322a693d800 · report
fixture: signature rays:Tensor/2/float, near:float/0/float, far:float/0/float, steps:int/0/int, lindisp:bool/0/bool, perturb:float/0/float · returned tuple · level recorded 2026-09-22 5c0af089509a5195 · report
fixture: returned Tensor · level recorded 2026-09-22 2f76a86e3e1b1c50 · report
fixture: signature x:Tensor/3/float, ref:Tensor/3/float · returned Tensor · level recorded 2026-09-22 31e9359f618551ac · report
fixture: signature model:callable/0/?, cam:StandInCamera/0/?, crop:tuple/1/int, size:int/0/int, args:StandInArgs/0/?, times:NoneType/0/?, with_noise:float/0/float · returned tuple · level recorded 2026-09-22 6bb87af4d7775276 · report
fixture: signature alphas:Tensor/2/float · returned Tensor · level recorded 2026-09-22 76043c73feb0d5bc · report
fixture: signature nerf_model:callable/0/?, ray_origins:Tensor/2/float, ray_directions:Tensor/2/float, hn:int/0/int, hf:float/0/float, nb_bins:int/0/int · returned Tensor · level recorded 2026-09-22 72ae52782cdecbe7 · report
355a63e6de028c93 · report
fixture: signature batch:list/1/SimpleData, tensor_collator:callable/0/? · returned SimpleData · level recorded 2026-09-22 b0ddc73a6106f3b5 · report
9fa6773feb9a0f57 · report
fixture: signature cam_poses:ndarray/3/float, offset:tuple/1/float, rotation:tuple/1/int · returned ndarray · level recorded 2026-09-24 e880e929a516e218 · report
fixture: signature azimuths:Tensor/2/float, zeniths:Tensor/2/float · returned Tensor · level recorded 2026-09-24 35565da1dac960eb · report
fixture: signature azimuths:Tensor/2/float, zeniths:Tensor/2/float, rad:float/0/float · returned Tensor · level recorded 2026-09-25 834db3a0c6566522 · report
fixture: signature x1:Tensor/3/float, x2:Tensor/3/float · returned Tensor · level recorded 2026-09-24 dd6690a28620c0d8 · report
fixture: signature raw:Tensor/3/float, z_vals:Tensor/2/float, rays_d:Tensor/2/float, raw_noise_std:float/0/float, white_bkgd:bool/0/bool, pytest:bool/0/bool · returned tuple · level recorded 2026-09-24 7ecb7076c29cd0d3 · report
fixture: signature x:Tensor/2/float · returned ndarray · level recorded 2026-09-25 f5a330da29e2f8e9 · report
fixture: signature x:ndarray/2/complex · returned Tensor · level recorded 2026-09-24 b7bd14e91d2770c0 · report
fixture: signature rays_o:Tensor/2/float, rays_d:Tensor/2/float, cam_id:int/0/int, rotation:dict/0/?, offset:dict/0/? · returned tuple · level recorded 2026-09-22 2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
census: 6 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket repository not located ran · our draft was wrong licence of this copy not recorded ·
fd57e365830d09de · report
fixture: signature fn:callable/0/?, chunk:int/0/int · returned function · level recorded, date not recorded 8f235fb889b93174 · report
fixture: signature inputs:Tensor/3/float, viewdirs:Tensor/2/float, fn:callable/0/?, embed_fn:callable/0/?, embeddirs_fn:callable/0/?, netchunk:int/0/int · returned Tensor · level recorded, date not recorded Tasks
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Low-Dose X-Ray Ct Reconstruction | X3D | NeRF | PSNR | 32.15 | #7 of 9 | Archive leaderboard | report |
| Low-Dose X-Ray Ct Reconstruction | X3D | NeRF | SSIM | 0.9354 | #7 of 9 | Archive leaderboard | report |
| Novel View Synthesis | X3D | NeRF | PSNR | 32.49 | #5 of 6 | Archive leaderboard | report |
| Novel View Synthesis | X3D | NeRF | SSIM | 0.9770 | #5 of 6 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections