Signals 4 · free daily AI digest

DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting

Paper recorded by Signals 4 on 2026-09-01 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-01 on arXiv · recorded by Signals 4 on 2026-09-02

Category: cs.CV · 计算机视觉 · first seen 2026-09-02

Abstract

While 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction and novel-view synthesis, scenarios with limited input views often lead to poor reconstruction quality and artifacts in rendered novel views. Recent efforts attempt to utilize powerful diffusion priors, yet they typically process rendered and reference views concatenated along an additional dimension in a single network. These

Read on arXiv →

#182 most recent of 237 cs.CV papers we have recorded · ↑ newer: Revisiting Cross-View Completion: Self-Supervised Pre-Training via Rec · ↓ older: A Sensor-Adaptive Incremental Learning Framework for Artifact Detectio
Cite this page: DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting: the #182 most recent of 237 cs.CV papers we have recorded (as of 2026-09-01). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/dualdiff3d-dual-structure-appearance-diffusion-priors-for-reliability-enhanced-3.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions