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
AESplat is a new pose‑free feed‑forward 3D Gaussian Splatting framework that improves rendering quality by decoupling view‑independent and view‑dependent appearance modeling. It directly extracts the base view‑independent appearance from input images and predicts higher‑order spherical harmonic coefficients with a shallow MLP that incorporates 3D‑aware inductive biases. Experiments on several datasets show AESplat outperforms state‑of‑the‑art methods, achieving up to 0.8 dB higher PSNR than NAS3R and 1.1 dB over DepthSplat on RealEstate10K.
By Shiwei Ren, Zhiang Liu, Yongchun Fang, Hongwei Chen
arXiv:2610.09853v1 Announce Type: new
Abstract: Pose-free feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene from sparse, unposed images in a single network pass, removing the need for ca...
By Chanung Park, Seunghyeon Song, Joo Chan Lee, Eunbyung Park, Jong Hwan Ko
arXiv:2511.16030v3 Announce Type: replace
Abstract: 3D Gaussian Splatting (3DGS) enables efficient, high-fidelity novel view synthesis, yet its performance degrades severely under sparse-view supervi...
By Zijian Wu, Mingfeng Jiang, Zidian Lin, Ying Song, Ziqian Lu, Qun Wu, Hanjie Ma
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.
By Xi Chen, Yachi Zhang, Linghao Chen, Minghua Liu, Hao Su, Zexiang Xu, Xiaoshuai Zhang
arXiv:2609.18034v1 Announce Type: new
Abstract: Novel view synthesis from unposed multi-view images remains challenging, as the model must jointly learn scene representations and camera parameters wi...
By Wenyu Li, Sidun Liu, Peng Qiao, Yong Dou, Tongrui Hu
arXiv:2609.23182v1 Announce Type: new
Abstract: Feed-forward 3D Gaussian Splatting now reconstructs renderable scenes from unposed, uncalibrated images. Yet, most models supervise only photometric co...
By Si-Yu Lu, Yung-Yao Chen, Yi Jan Chen, Shang-Lin Li, Ching-Chan Liao, Wen-Huang Cheng
arXiv:2610.09173v1 Announce Type: new
Abstract: 3D foundation models enable efficient novel view synthesis by carrying a Gaussian head on the representation they already use for reconstruction. Howev...
By Zhijie Zheng, Xinhao Xiang, Jiawei Zhang
arXiv:2608.30342v1 Announce Type: new
Abstract: 3D Gaussian Splatting (3DGS) enables photorealistic real-time novel view synthesis, yet placing a virtual camera to capture a desired frame remains lar...
By Jirong Li, Satoshi Ikehata, Shuhei Kurita, Ikuro Sato
The paper presents a training‑free filtering method for feed‑forward 3D Gaussian Splatting that removes transient distractors from 3D reconstructions. By excluding each input’s per‑view Gaussians and re‑rendering the scene, the method identifies inconsistent content through feature similarity and reconstruction error reduction. The approach improves novel‑view quality across multiple models and benchmarks while preserving clean scenes.
By Kangmin Seo, Jae-Pil Heo
arXiv:2610.07958v1 Announce Type: new
Abstract: Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene in a single forward pass, replacing per-scene optimization with a network trained across...
By Minhyeok Lee, Jungho Lee, Minseok Kang, Heeseung Choi, Ig-Jae Kim, Sangyoun Lee
PIVOT is a new multi‑trajectory dataset and evaluation framework that captures real‑world scenes with diverse camera paths, preserving both sensor‑derived measured poses and COLMAP‑optimized poses along with calibrated and optimized intrinsics. It defines three benchmark families—seen vs. unseen trajectory generalization, measured vs. optimized pose sensitivity, and calibrated vs. optimized intrinsics sensitivity—and introduces a directed pose‑space Chamfer distance to assess pose coverage. The first version of PIVOT includes five scenes recorded with a DJI Mini 4 Pro and offers an open processing and Nerfstudio‑based evaluation toolchain, revealing a consistent quality gap between held‑out and unseen trajectories and significant sensitivity to pose source and camera intrinsics.
By Mary Raymond