arXiv Computer Vision
SG-Splat: Stable Geometry Learning under Pose Uncertainty for Pose-Free 3D Gaussian Splatting
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Oct 8
DeltaSplat: Iterative Gaussian Refinement for Pose-Free Feed-Forward 3D Gaussian Splatting
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...
arXiv AI
2d ago
Aligning Misaligned Benchmarks for Single-View Novel View Synthesis
The paper addresses the lack of standardized evaluation for single‑view novel view synthesis by highlighting the importance of aligning a method’s reference frame with the ground‑truth camera pose. It proposes using traditional 2D‑to‑2D and 2D‑to‑3D image matching to align 3D reconstructions and restricts evaluation to co‑visible regions where a correct ground truth exists. Experiments show that with proper alignment, 3D Gaussian‑based methods reach state‑of‑the‑art performance, and a simple baseline using a video generator and geometry estimator matches specialized novel‑view synthesis models without task‑specific training.
arXiv Computer Vision
Oct 21
CrossFit-GS: Out-of-Fold Pose Estimation for COLMAP-Free 3D Gaussian Splatting
CrossFit-GS is a new framework for pose-free 3D Gaussian Splatting that avoids the need for Structure-from-Motion by directly reconstructing scenes from unposed image sequences. The method partitions the input into interleaved subsets, maintaining two complementary submaps and cross-refining candidate poses against a frozen opposite submap to provide an independent geometric reference. Additional checkerboard validation and spatial coverage safeguards reject unreliable updates, and only verified poses are committed; after refinement, the final global representation is trained from scratch using the fixed refined poses, leading to reduced trajectory drift and improved camera pose estimation and novel-view synthesis across multiple benchmarks.
arXiv Computer Vision
Sep 16
Unlocking Zero-shot Potential of Semi-dense Image Matching via Gaussian Splatting
arXiv:2511.21265v2 Announce Type: replace Abstract: Learning-based image matching critically depends on large-scale, diverse, and geometrically accurate training data. 3D Gaussian Splatting (3DGS) en...
arXiv Computer Vision
Oct 19
Frame-Consistent Feed-Forward 3D Gaussian Splatting from Sparse Unposed Images
arXiv:2610.23039v1 Announce Type: new Abstract: Feed-forward Gaussian models have made novel view synthesis almost instantaneous. Feed-forward methods predict Gaussians directly, either in two stages...
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.