← Back to all news
arXiv Computer Vision

LVSPM: Long Sequence View Synthesis and Pose Estimation Model

LVSPM is a generalizable model that jointly estimates camera poses and synthesizes novel views from uncalibrated image collections. It is trained only with RGB images and pose supervision, avoiding dense 3D ground truth, and uses test‑time training layers to scale to hundreds of input views. On datasets such as RealEstate10k, Co3Dv2, and DL3DV, LVSPM outperforms VGGT in pose estimation across 16–256 views and achieves state‑of‑the‑art pose‑free novel view synthesis quality, maintaining high performance even as scene scale increases.

Related stories

arXiv Computer Vision
3d ago

Benchmarking Efficient & Effective Camera Pose Estimation Strategies for Novel View Synthesis

The paper introduces a benchmark for evaluating Structure-from-Motion (SfM) methods used in novel view synthesis (NVS) such as NeRFs and 3DGS. It compares classical SfM, which relies on local feature matches and bundle adjustment, with recent neural network approaches that regress camera parameters directly for faster but less accurate results. The study finds that reducing feature counts speeds up classical SfM without sacrificing pose accuracy, and that combining neural network initial estimates with classical refinement yields the best balance of efficiency and effectiveness.

By Jhacson Meza, Martin R. Oswald, Torsten Sattler
llmscomputer-visionbenchmarks
More like this →
arXiv Computer Vision
Sep 25

One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation

The paper introduces OVIE, a monocular novel-view synthesis method that eliminates the need for multi‑view training data. By using a frozen depth estimator to generate pseudo‑target views from single images and applying masked and adversarial losses, OVIE is trained on 30 million uncurated images. It achieves state‑of‑the‑art performance on RealEstate10K and DL3DV, produces highly consistent multi‑view trajectories, and runs at 116 FPS—over 600× faster than the fastest baseline.

By Adrien Ramanana Rahary, Nicolas Dufour, Patrick Perez, David Picard
fine-tuningsafety
More like this →
arXiv AI
Sep 21

Think Locally, Refine Globally for Memory-Efficient 3D Reconstruction

LoG-VGGT is a memory‑efficient framework for long‑sequence 3D reconstruction that balances local temporal modeling with global camera consistency. It uses cross‑window attention in a small subset of transformer blocks to propagate information across adjacent temporal windows while keeping memory usage bounded. A global camera consistency refinement module further improves long‑horizon pose stability by enforcing scene‑level constraints through cross‑attention between camera and compact register tokens, leading to better depth accuracy and robust camera pose estimation on multiple benchmarks.

By Jingke Zhou, Chenhang Ma, Zhizhou Zhong, Mingkai Liu, Zhuang Zhou, Yicheng ji, Binghua Su, Bo Cai, Xianliang Huang
llmscomputer-visionbenchmarks
More like this →
arXiv Computer Vision
Sep 4

Stabilizing Camera-Controlled Novel View Synthesis at Inference Time

The paper introduces CamTrol++, a training‑free method that stabilizes camera‑controlled novel view synthesis from a single image by decomposing large camera motions into small autoregressive steps, thereby limiting per‑step distortion and error accumulation. It also incorporates geometry‑constrained spatial attention, low‑frequency appearance anchoring, and a registration‑free warping pipeline to further enhance stability. Experiments on RealEstate10K and MegaScene demonstrate improved temporal and geometric consistency, better downstream 3D reconstruction quality, and higher generation efficiency, even for long 56‑frame sequences and under depth corruption.

By Prajwal Singh, Arjun Badola, Seema Kumari, Hajime Nagahara, Shanmuganathan Raman
diffusion
More like this →
arXiv Computer Vision
Sep 21

VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization

VoxelTTO is a feed‑forward framework that reconstructs 3D Gaussian splatting scenes from multiple images by aggregating dense image features into a global voxel representation and decoding Gaussians from voxel features, thereby eliminating the pixel‑to‑Gaussian correspondence. It incorporates test‑time optimization with lightweight LoRA modules to adapt to known camera parameters while keeping the pretrained visual foundation model frozen. The method replaces standard rasterization with stochastic solid volume rendering, improving geometric fidelity, and demonstrates superior RGB‑D novel‑view synthesis and camera‑pose estimation on Replica, Tanks and Temples, and DTU datasets.

By Yibin Zhao, Yihan Pan, Yangwen Li, Jun Nan, Jianjun Yi
computer-visionfine-tuning
More like this →
arXiv Computer Vision
Sep 3

RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation

RoGe is a new end‑to‑end framework for novel view synthesis that jointly learns an implicit 3D scene representation and a video diffusion model. It eliminates the need for explicit 3D intermediates by querying the implicit scene with camera rays to produce geometric features that condition the diffusion model. Experiments on DL3DV show that RoGe surpasses reconstruction‑based, generation‑based, and hybrid baselines in image quality and temporal consistency, and ablations confirm the benefits of ray‑queried features and joint training.

By Xiaolei Lang, Ze Kang, Zehao Huang, Naiyan Wang
diffusion
More like this →