paper-with-me

Papers

Enhancing Novel View Synthesis via Geometry Grounded Set Diffusion

2026-01-12 · Farhad G. Zanjani, Hong Cai, Amirhossein Habibian arxiv

We present SetDiff, a geometry-grounded multi-view diffusion framework that enhances novel-view renderings produced by 3D Gaussian Splatting. Our method integrates explicit 3D priors, pixel-aligned coordinate maps and pose-aware Plucker ray embeddings, into a set-based diffusion model capable of jointly processing variable numbers of reference and target views. This formulation enables robust occlusion handling, reduces hallucinations under low-signal conditions, and improves photometric fidelity in visual content restoration. A unified set mixer performs global token-level attention across all input views, supporting scalable multi-camera enhancement while maintaining computational efficiency through latent-space supervision and selective decoding. Extensive experiments on EUVS, Para-Lane, nuScenes, and DL3DV demonstrate significant gains in perceptual fidelity, structural similarity, and robustness under severe extrapolation. SetDiff establishes a state-of-the-art diffusion-based solution for realistic and reliable novel-view synthesis in autonomous driving scenarios.

📄 PDF Abstract BibTeX arXiv:2601.07540

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyNovel View SynthesisAutonomous Driving

Similar Papers 제목 키워드 기반

GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis

2026-03-16 · Minjun Kang, Inkyu Shin, Taeyeop Lee, Myungchul Kim 외 arxiv

Novel view synthesis requires strong 3D geometric consistency and the ability to generate visually coherent images across diverse viewpoints. While recent camera-controlled video diffusion models show promising results, …

Novel View Synthesis

MagicDrive: Street View Generation with Diverse 3D Geometry Control

2023-10-04 · Ruiyuan Gao, Kai Chen, Enze Xie, Lanqing Hong 외

Recent advancements in diffusion models have significantly enhanced the data synthesis with 2D control. Yet, precise 3D control in street view generation, crucial for 3D perception tasks, remains elusive. Specifically, u…

3D geometry3D Object DetectionBEV SegmentationObject+2

MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement

2024-08-26 · Xu He, Xiaoyu Li, Di Kang, Jiangnan Ye 외

Existing works in single-image human reconstruction suffer from weak generalizability due to insufficient training data or 3D inconsistencies for a lack of comprehensive multi-view knowledge. In this paper, we introduce …

3D Human ReconstructionNovel View Synthesis

DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion

2026-05-16 · Yuhan Ping, Yuan Liu, Xiaoxiao Long, Peng Wang 외 arxiv

In this paper, we introduce \textit{DecoRec}, a novel system designed to elevate single-view 2D images to a decomposed 3D scene mesh. Current methods for single-view scene reconstruction typically rely on object retrieva…

Scene Generation

PanoPlane: Plane-Aware Panoramic Completion for Sparse-View Indoor 3D Gaussian Splatting

2026-05-13 · Adil Qureshi, Dongki Jung, Jaehoon Choi, Dinesh Manocha arxiv

We present PanoPlane, an approach for high-fidelity sparse-view indoor novel view synthesis that reconstructs closed room geometry via panoramic scene completion. Unlike perspective-based methods that generate training v…

Novel View Synthesis