Papers › Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video

Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video

27 Mar 2025CVPR 2025 1arXiv:2503.21761archive 2025-07-28

David Yifan Yao, Albert J. Zhai, Shenlong Wang

This paper presents a unified approach to understanding dynamic scenes from casual videos. Large pretrained vision foundation models, such as vision-language, video depth prediction, motion tracking, and segmentation models, offer promising capabilities. However, training a single model for comprehensive 4D understanding remains challenging. We introduce Uni4D, a multi-stage optimization framework that harnesses multiple pretrained models to advance dynamic 3D modeling, including static/dynamic reconstruction, camera pose estimation, and dense 3D motion tracking. Our results show state-of-the-art performance in dynamic 4D modeling with superior visual quality. Notably, Uni4D requires no retraining or fine-tuning, highlighting the effectiveness of repurposing visual foundation models for 4D understanding.

PaperPDFConference PDFCodeCode Syntology ran

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):

Code

Syntology 18 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 15 ran (14 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Davidyao99/uni4d officialmentioned on GitHubpytorchMITSyntology: 18 samples, 15 ran (1 instrument-failed) · 3 unverified report

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.

Code Syntology ran Syntology

18 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 3 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.

1ran · our draft was wrong
14ran
3unverified

Licence: 1 of the 18 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 Davidyao99/uni4d. “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.

Davidyao99/uni4d official repository 18 samples, 15 ran (1 instrument-failed) · 3 unverified
absolute_error_loss uni4d/eval_depth.py ran MIT (permissive) · 6dc0a401faa181c2 · report fixture: signature params:tuple/1/float, predicted_depth:ndarray/2/float, ground_truth_depth:ndarray/2/float · returned float32 · level recorded 2026-09-25
absolute_value_scaling uni4d/eval_depth.py ran MIT (permissive) · 071060ffd8045cf0 · report fixture: signature predicted_depth:Tensor/2/float, ground_truth_depth:Tensor/2/float, s:float/0/float, t:float/0/float · returned tuple · level recorded 2026-09-25
convert_trajectory_to_extrinsic_matrices dataset_prepare/util.py ran MIT (permissive) · 3470bb7f3951b38c · report fixture: signature positions:ndarray/2/float, quaternions_xyzw:ndarray/2/float · returned ndarray · level recorded 2026-09-25
depth2disparity uni4d/eval_depth.py ran fingerprinted MIT (permissive) · 7d031b19941d06f5 · report fixture: signature depth:Tensor/2/float, return_mask:bool/0/bool · returned Tensor · level recorded 2026-09-25
depth_read dataset_prepare/sintel_io.py ran MIT (permissive) · a88685769d5ff548 · report fixture: signature filename:str/0/str · returned ndarray · level recorded 2026-09-24
depth_vis uni4d/util.py ran MIT (permissive) · 0cbc9f11c671557a · report fixture: returned ndarray · level recorded 2026-09-25
disparity_read dataset_prepare/sintel_io.py ran MIT (permissive) · e162442d5908bd04 · report fixture: signature filename:str/0/str · returned ndarray · level recorded 2026-09-24
find_closest_index dataset_prepare/preprocess_tumd.py ran fingerprinted MIT (permissive) · 959323d9f907ca0b · report fixture: signature L:list/1/float, t:float/0/float · returned int · level recorded 2026-09-25
flow_norm uni4d/util.py ran MIT (permissive) · 0bf2c9084103deab · report fixture: signature flow:Tensor/4/float, is_l1:bool/0/bool · returned Tensor · level recorded 2026-09-25
flow_read dataset_prepare/sintel_io.py ran MIT (permissive) · a976c9053fc1681f · report fixture: signature filename:str/0/str · returned tuple · level recorded 2026-09-24
get_gt in 7 papers uni4d/eval_pose.py ran MIT (permissive) · af61a94065b60b27 · report fixture: signature video_path:str/0/str · returned tuple · level recorded 2026-09-24
get_preds in 18 papers uni4d/eval_pose.py ran MIT (permissive) · d8e70a5c3026ef98 · report fixture: signature video_path:str/0/str, model:str/0/str, experiment_name:str/0/str, number_of_frames:int/0/int · returned tuple · level recorded 2026-09-25
quaternion_to_matrix in 10 papers uni4d/variables.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 000b3a2e5186a974 · report fixture: signature quaternions:Tensor/2/float · returned Tensor · level recorded 2026-09-24
read_trajectory in 5 papers dataset_prepare/preprocess_tumd.py ran MIT (permissive) · 339c20f5ac123bcc · report fixture: signature filename:str/0/str, matrix:bool/0/bool · returned dict · level recorded 2026-09-25
signed_expm1 uni4d/variables.py ran fingerprinted MIT (permissive) · 68275a37f3c13918 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-25
fill_depth_nearest uni4d/util.py unverified MIT (permissive) · 67bfa3f61f955ce1 · report
hat uni4d/variables.py unverified MIT (permissive) · 9ffd7c4d7dfde3e9 · report
transform44 dataset_prepare/preprocess_tumd.py unverified MIT (permissive) · b63ff70118c24067 · report

Tasks

Camera Pose EstimationDepth EstimationDepth PredictionDynamic ReconstructionPose Estimation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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