REVIEW 9 cited by
Learning Temporally Consistent Video Depth from Video Diffusion Priors
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Learning Temporally Consistent Video Depth from Video Diffusion Priors
read the original abstract
This work addresses the challenge of streamed video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. We argue that sharing contextual information between frames or clips is pivotal in fostering temporal consistency. Therefore, we reformulate depth prediction into a conditional generation problem to provide contextual information within a clip and across clips. Specifically, we propose a consistent context-aware training and inference strategy for arbitrarily long videos to provide cross-clip context. We sample independent noise levels for each frame within a clip during training while using a sliding window strategy and initializing overlapping frames with previously predicted frames without adding noise. Moreover, we design an effective training strategy to provide context within a clip. Extensive experimental results validate our design choices and demonstrate the superiority of our approach, dubbed ChronoDepth. Project page: https://xdimlab.github.io/ChronoDepth/.
Forward citations
Cited by 9 Pith papers
-
Forget, Anticipate and Adapt: Test Time Training for Long Videos
FFN enables efficient TTT for long videos by operating on three frames and using a surprise-based adaptive window, shown on a new dataset of up to 3-hour videos for segmentation and classification tasks.
-
Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation
Hallo4D uses vision-language models to detect and correct spatial and temporal mistakes in AI-generated 3D and 4D content, improving consistency without retraining the base generators.
-
Forget, Anticipate and Adapt: Test Time Training for Long Videos
FFN performs TTT on multi-hour videos by restricting updates to three frames and using a surprise metric for adaptive window sizing, plus a new EpicTours dataset.
-
Forget, Anticipate and Adapt: Test Time Training for Long Videos
FFN performs efficient test-time training on multi-hour videos by forgetting the exiting frame, anticipating the next, and adapting only when a surprise metric exceeds a dynamic threshold.
-
Towards Consistent Video Geometry Estimation
One transformer, trained with random-sized temporal attention chunks, unifies offline, streaming, and long-video depth, normal, and point-map estimation and reports new best numbers on five public benchmarks.
-
Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation
Hallo4D mitigates 3D/4D generation hallucinations via LMM-based detection, multi-model voting correction, and motion-aware optimization without retraining base generators.
-
Towards Consistent Video Geometry Estimation
ViGeo is a feed-forward transformer for video geometry that introduces dynamic chunking attention and a completion-based data refinement framework to achieve SOTA on depth, normals, and point map estimation.
-
Geometry-aware 4D Video Generation for Robot Manipulation
A geometry-aware 4D video generation model trained with cross-view pointmap alignment to produce spatio-temporally consistent future videos from novel viewpoints for robot manipulation.
-
MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
By fine-tuning DUST3R to output per-timestep pointmaps on scarce dynamic video datasets, MonST3R achieves stronger video depth and pose estimation without explicit motion modeling.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.