Papers › Streaming 4D Visual Geometry Transformer

Streaming 4D Visual Geometry Transformer

15 Jul 2025arXiv:2507.11539archive 2025-07-28

Dong Zhuo, Wenzhao Zheng, Jiahe Guo, Yuqi Wu, Jie zhou, Jiwen Lu

Perceiving and reconstructing 4D spatial-temporal geometry from videos is a fundamental yet challenging computer vision task. To facilitate interactive and real-time applications, we propose a streaming 4D visual geometry transformer that shares a similar philosophy with autoregressive large language models. We explore a simple and efficient design and employ a causal transformer architecture to process the input sequence in an online manner. We use temporal causal attention and cache the historical keys and values as implicit memory to enable efficient streaming long-term 4D reconstruction. This design can handle real-time 4D reconstruction by incrementally integrating historical information while maintaining high-quality spatial consistency. For efficient training, we propose to distill knowledge from the dense bidirectional visual geometry grounded transformer (VGGT) to our causal model. For inference, our model supports the migration of optimized efficient attention operator (e.g., FlashAttention) from the field of large language models. Extensive experiments on various 4D geometry perception benchmarks demonstrate that our model increases the inference speed in online scenarios while maintaining competitive performance, paving the way for scalable and interactive 4D vision systems. Code is available at: https://github.com/wzzheng/StreamVGGT.

PaperPDFCodeCode 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 13 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 5 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 13 ran (8 with no instrument failure; 5 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 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

wzzheng/streamvggt officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 13 samples, 13 ran (5 instrument-failed) · 0 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

13 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 0 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.

2ran · honoured contract
5ran; the contract check could not run
6ran

Licence: 13 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from wzzheng/streamvggt. “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.

wzzheng/streamvggt official repository 13 samples, 13 ran (5 instrument-failed) · 0 unverified
activate_head src/streamvggt/heads/head_act.py ran licence not identified · pointer only · 6e3d1e3fa82b57d9 · report fixture: signature out:Tensor/4/float, activation:str/0/str, conf_activation:str/0/str · returned tuple · level recorded 2026-09-25
activate_pose src/streamvggt/heads/head_act.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 732f3a3c6b94593c · report fixture: signature pred_pose_enc:Tensor/2/float, trans_act:str/0/str, quat_act:str/0/str, fl_act:str/0/str · returned Tensor · level recorded 2026-09-25
add_residual in 18 papers src/streamvggt/layers/block.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 5d16d4d4fc573ac7 · report fixture: signature x:Tensor/2/float, brange:Tensor/1/int, residual:Tensor/2/float, residual_scale_factor:float/0/float, scaling_vector:NoneType/0/? · returned Tensor · level recorded 2026-09-26
base_pose_act src/streamvggt/heads/head_act.py ran; the contract check could not run (RAISES) no licence file found · pointer only · b881c649136fa014 · report fixture: signature pose_enc:Tensor/2/float, act_type:str/0/str · returned Tensor · level recorded 2026-09-22
create_uv_grid src/streamvggt/heads/utils.py ran licence not identified · pointer only · ec669c1b58089748 · report fixture: signature width:int/0/int, height:int/0/int, aspect_ratio:float/0/float, dtype:dtype/0/?, device:device/0/? · returned Tensor · level recorded 2026-09-25
custom_interpolate src/streamvggt/heads/dpt_head.py ran licence not identified · pointer only · f43a4f443063d830 · report fixture: signature x:Tensor/4/float, size:tuple/1/int, scale_factor:NoneType/0/?, mode:str/0/str, align_corners:bool/0/bool · returned Tensor · level recorded 2026-09-25
drop_add_residual_stochastic_depth in 26 papers src/streamvggt/layers/block.py ran licence not identified · pointer only · a2ec87bca0ee4781 · report fixture: signature x:Tensor/3/float, residual_func:callable/0/?, sample_drop_ratio:float/0/float, pos:Tensor/3/float · returned Tensor · level recorded 2026-09-25
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
src/streamvggt/layers/drop_path.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · c157f5b112b3a392 · report fixture: signature x:Tensor/4/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
get_branges_scales in 18 papers src/streamvggt/layers/block.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 5be3610fa1fee19e · report fixture: signature x:Tensor/3/float, sample_drop_ratio:float/0/float · returned tuple · level recorded 2026-09-26
make_2tuple in 21 papers src/streamvggt/layers/patch_embed.py ran · honoured contract fingerprinted no licence file found · pointer only · 3c04490a215299f2 · report fixture: signature x:int/0/int · returned tuple · level recorded 2026-09-22
make_sincos_pos_embed src/streamvggt/heads/utils.py ran licence not identified · pointer only · 731bd479ffcd13a9 · report fixture: signature embed_dim:int/0/int, pos:Tensor/1/float, omega_0:float/0/float · returned Tensor · level recorded 2026-09-25
modulate in 137 papers
census: 3 implementations from 12 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32
src/streamvggt/heads/camera_head.py ran · honoured contract fingerprinted no licence file found · pointer only · ed311bf19f15387b · report fixture: signature x:Tensor/2/float, shift:Tensor/2/float, scale:Tensor/2/float · returned Tensor · level recorded 2026-09-22
position_grid_to_embed src/streamvggt/heads/utils.py ran licence not identified · pointer only · 910e268f54177e2b · report fixture: signature pos_grid:Tensor/3/float, embed_dim:int/0/int, omega_0:float/0/float · returned Tensor · level recorded 2026-09-25

Tasks

4D reconstructionPhilosophy

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SPEED

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