Pith. sign in

REVIEW 5 cited by

A Compact Dynamic 3D Gaussian Representation for Real-Time Dynamic View Synthesis

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2311.12897 v2 pith:HQOMUZ47 submitted 2023-11-21 cs.GR

Kai Katsumata , Duc Minh Vo , Hideki Nakayama This is my paper · ORCID
classification cs.GR
keywords dynamicgaussianrenderingcompactmemorymethodmulti-viewrepresentation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

3D Gaussian Splatting (3DGS) has shown remarkable success in synthesizing novel views given multiple views of a static scene. Yet, 3DGS faces challenges when applied to dynamic scenes because 3D Gaussian parameters need to be updated per timestep, requiring a large amount of memory and at least a dozen observations per timestep. To address these limitations, we present a compact dynamic 3D Gaussian representation that models positions and rotations as functions of time with a few parameter approximations while keeping other properties of 3DGS including scale, color and opacity invariant. Our method can dramatically reduce memory usage and relax a strict multi-view assumption. In our experiments on monocular and multi-view scenarios, we show that our method not only matches state-of-the-art methods, often linked with slower rendering speeds, in terms of high rendering quality but also significantly surpasses them by achieving a rendering speed of $118$ frames per second (FPS) at a resolution of 1,352$\times$1,014 on a single GPU.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Monocular Dynamic Gaussian Splatting: Fast, Brittle, and Scene Complexity Rules

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A comprehensive benchmark shows monocular dynamic Gaussian splatting methods are fast and brittle, with scene complexity dominating method differences.

  2. DGNS: Deformable Gaussian Splatting and Dynamic Neural Surface for Monocular Dynamic 3D Reconstruction

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A hybrid of deformable Gaussian splatting and dynamic neural SDF achieves state-of-the-art 3D mesh accuracy from monocular video while keeping view synthesis competitive.

  3. 3D Gaussian Representations with Motion Trajectory Field for Dynamic Scene Reconstruction

    cs.RO 2025-08 conditional novelty 5.0 of 10

    A 3D Gaussian Splatting model whose Gaussian centers are represented as a learned combination of shared global motion bases recovers dynamic scenes and motion trajectories from monocular video.

  4. Advancing Extended Reality with 3D Gaussian Splatting: Innovations and Prospects

    cs.CV 2024-12 conditional novelty 4.0 of 10

    3D Gaussian Splatting research relevant to Extended Reality is organized into a five-part taxonomy with suggested future directions.

  5. AI-Driven Innovations in Volumetric Video Streaming: A Review

    cs.CV 2024-12 conditional novelty 3.0 of 10

    A survey that categorizes AI methods for volumetric video streaming by representation type and identifies open challenges in bandwidth, rendering latency, and dynamic scenes.

Pith tools