Pith. sign in

REVIEW 6 cited by

DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting

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 2312.00112 v2 pith:VC3UVULH submitted 2023-11-30 cs.CV cs.GR

classification cs.CVcs.GR
keywords dynamicmotionscenemotionsneuralrepresentationscenestrajectories
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Accurately and efficiently modeling dynamic scenes and motions is considered so challenging a task due to temporal dynamics and motion complexity. To address these challenges, we propose DynMF, a compact and efficient representation that decomposes a dynamic scene into a few neural trajectories. We argue that the per-point motions of a dynamic scene can be decomposed into a small set of explicit or learned trajectories. Our carefully designed neural framework consisting of a tiny set of learned basis queried only in time allows for rendering speed similar to 3D Gaussian Splatting, surpassing 120 FPS, while at the same time, requiring only double the storage compared to static scenes. Our neural representation adequately constrains the inherently underconstrained motion field of a dynamic scene leading to effective and fast optimization. This is done by biding each point to motion coefficients that enforce the per-point sharing of basis trajectories. By carefully applying a sparsity loss to the motion coefficients, we are able to disentangle the motions that comprise the scene, independently control them, and generate novel motion combinations that have never been seen before. We can reach state-of-the-art render quality within just 5 minutes of training and in less than half an hour, we can synthesize novel views of dynamic scenes with superior photorealistic quality. Our representation is interpretable, efficient, and expressive enough to offer real-time view synthesis of complex dynamic scene motions, in monocular and multi-view scenarios.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

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

  1. ClipGStream: Clip-Stream Gaussian Splatting for Any Length and Any Motion Multi-View Dynamic Scene Reconstruction

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    ClipGStream enables scalable flicker-free reconstruction of long dynamic multi-view videos by performing stream optimization at the clip level with clip-independent spatio-temporal fields, residual anchor compensation...

  2. Realizing Immersive Volumetric Video: A Multimodal Framework for 6-DoF VR Engagement

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    The paper presents a multimodal framework, dataset, and reconstruction pipeline to create immersive volumetric videos supporting large 6-DoF audiovisual interaction from real multi-view captures.

  3. 4DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humans

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A diffusion model trained on 60,000 fitted 4D Gaussian Splatting human clips generates text-prompted, view-consistent dynamic humans directly in 4D, over 10x faster than video-first pipelines.

  4. 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.

  5. LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling

    cs.CV 2025-07 conditional novelty 5.0 of 10

    LocalDyGS reconstructs dynamic scenes by decomposing space into seed-based local regions and generating time-varying Temporal Gaussians, though its claim of being first for large-scale scenes omits the existing Swift4...

  6. A Survey on 3D Gaussian Splatting

    cs.CV 2024-01 unverdicted novelty 2.0 of 10

    A survey compiling principles, applications, benchmarks, and challenges of 3D Gaussian Splatting for explicit 3D scene representation.

Pith tools