Pith. sign in

REVIEW 2 cited by

Predicting 3D representations for Dynamic Scenes

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

arxiv 2501.16617 v1 pith:755JSKKY submitted 2025-01-28 cs.CV

Predicting 3D representations for Dynamic Scenes

classification cs.CV
keywords dynamicmodelmonoculardesignsfieldframeworkphysicalpredicting
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We present a novel framework for dynamic radiance field prediction given monocular video streams. Unlike previous methods that primarily focus on predicting future frames, our method goes a step further by generating explicit 3D representations of the dynamic scene. The framework builds on two core designs. First, we adopt an ego-centric unbounded triplane to explicitly represent the dynamic physical world. Second, we develop a 4D-aware transformer to aggregate features from monocular videos to update the triplane. Coupling these two designs enables us to train the proposed model with large-scale monocular videos in a self-supervised manner. Our model achieves top results in dynamic radiance field prediction on NVIDIA dynamic scenes, demonstrating its strong performance on 4D physical world modeling. Besides, our model shows a superior generalizability to unseen scenarios. Notably, we find that our approach emerges capabilities for geometry and semantic learning.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images

    cs.CV 2026-06 unverdicted novelty 6.0

    FFAvatar uses a Transformer-based 3D Gaussian model with alternating attention and sparse-to-dense learning to enable feed-forward, incremental reconstruction of animatable 4D head avatars from sparse portrait images.

  2. FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images

    cs.CV 2026-06 conditional novelty 6.0

    A Transformer 3D-Gaussian model reconstructs incremental, animatable 4D head avatars from sparse portraits via alternating attention, sparse-to-dense UV densification, and residual motion refinement.