paper-with-me

Papers

Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis

2025-01-06 · Thang-Anh-Quan Nguyen, Nathan Piasco, Luis Roldão, Moussab Bennehar, Dzmitry Tsishkou, Laurent Caraffa, Jean-Philippe Tarel, Roland Brémond

In this paper, we present PointmapDiffusion, a novel framework for single-image novel view synthesis (NVS) that utilizes pre-trained 2D diffusion models. Our method is the first to leverage pointmaps (i.e. rasterized 3D scene coordinates) as a conditioning signal, capturing geometric prior from the reference images to guide the diffusion process. By embedding reference attention blocks and a ControlNet for pointmap features, our model balances between generative capability and geometric consistency, enabling accurate view synthesis across varying viewpoints. Extensive experiments on diverse real-world datasets demonstrate that PointmapDiffusion achieves high-quality, multi-view consistent results with significantly fewer trainable parameters compared to other baselines for single-image NVS tasks.

📄 PDF Abstract BibTeX arXiv:2501.02913

Code (0)

등록된 구현이 없습니다.

Tasks

Novel View Synthesis

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps

2025-07-04 · Chong Cheng, Sicheng Yu, Zijian Wang, Yifan Zhou 외

3D Gaussian Splatting (3DGS) has become a popular solution in SLAM due to its high-fidelity and real-time novel view synthesis performance. However, some previous 3DGS SLAM methods employ a differentiable rendering pipel…

3DGSNovel View Synthesis

RGB-Only Gaussian Splatting SLAM for Unbounded Outdoor Scenes

2025-02-21 · Sicheng Yu, Chong Cheng, Yifan Zhou, Xiaojun Yang 외

3D Gaussian Splatting (3DGS) has become a popular solution in SLAM, as it can produce high-fidelity novel views. However, previous GS-based methods primarily target indoor scenes and rely on RGB-D sensors or pre-trained …

3DGSCamera Pose EstimationDepth EstimationNovel View Synthesis+2

unPIC: A Geometric Multiview Prior for Image to 3D Synthesis

2024-12-13 · Rishabh Kabra, Drew A. Hudson, Sjoerd van Steenkiste, Joao Carreira 외

We introduce a hierarchical probabilistic approach to go from a 2D image to multiview 3D: a diffusion "prior" predicts the unseen 3D geometry, which then conditions a diffusion "decoder" to generate novel views of the su…

3D geometryDecoderImage to 3DNovel View Synthesis

HumanGif: Single-View Human Diffusion with Generative Prior

2025-02-17 · Shoukang Hu, Takuya Narihira, Kazumi Fukuda, Ryosuke Sawata 외

While previous single-view-based 3D human reconstruction methods made significant progress in novel view synthesis, it remains a challenge to synthesize both view-consistent and pose-consistent results for animatable hum…

3D Human ReconstructionNeRFNovel View Synthesis

ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models

2023-12-03 · CVPR 2024 1 · Jeong-gi Kwak, Erqun Dong, Yuhe Jin, Hanseok Ko 외

Generating novel views of an object from a single image is a challenging task. It requires an understanding of the underlying 3D structure of the object from an image and rendering high-quality, spatially consistent new …

Novel View SynthesisObject