Research map / 3D vision / Gaussian splatting
AdaptiveSplat: Texture Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction
Badrinath Singhal, Srihari K G, Sreehari Iyer, Ankit Dhiman, Venkatesh Babu Radhakrishnan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add texture-based ranking of SuperClusters (ablation) | AdaptiveSplat · ACID beta=0.4 | PSNR: 21.31 -> 22.55 | Improved |
| add texture-based ranking of SuperClusters (ablation) | AdaptiveSplat · RE10K beta=0.4 | PSNR: 20.73 -> 22.29 | Improved |
| add trained Adaptive Gaussian Head (ablation) | AdaptiveSplat · ACID beta=0.4 | PSNR: 17.44 -> 22.55 | Improved |
| add trained Adaptive Gaussian Head (ablation) | AdaptiveSplat · RE10K beta=0.4 | PSNR: 19.81 -> 22.29 | Improved |
| add binary mask input to the head (ablation) | AdaptiveSplat · ACID beta=0.4 | PSNR: 22.52 -> 22.55 | No clear effect |
| add binary mask input to the head (ablation) | AdaptiveSplat · RE10K beta=0.4 | PSNR: 20.06 -> 22.29 | Improved |
| increase SuperClusters k from 50 to 400 (ablation) | AdaptiveSplat · ACID beta=0.4 | PSNR: 22.416 -> 22.559 | No clear effect |
| vary retention gamma from 0.10 to 0.05 or 0.15 (ablation) | AdaptiveSplat · ACID beta=0.4 | PSNR: 22.549 -> 21.796 (gamma 0.05); 22.549 -> 21.587 (gamma 0.15) | Hurt |
| use texture-aware pruning masks instead of LightGaussian masks, both with the adaptive head | AdaptiveSplat · ACID beta=0.4 | PSNR: 19.439 -> 22.549 | Improved |
| texture-aware pruning in place of InstantSplat native pruning | InstantSplat · Tanks and Temples Horse 10 views beta=0.8 | PSNR: 14.827 -> 27.178 | Improved |
| add adaptive head to MVSplat at beta=0 | MVSplat · ACID 2 views | PSNR: 25.31 -> 25.75 | Improved |
| increase pruning from beta=0.4 to 0.8 | AdaptiveSplat · ACID | PSNR: 22.549 -> 21.055 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- EAGLES — EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS (ECCV 2024) · better on 5 of 5 shared results
- LightGaussian — LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS (NeurIPS 2024) · better on 4 of 4 shared results
- PUP-3DGS — PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting (CVPR 2025) · better on 2 of 2 shared results
- MVSplat — MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images (ECCV 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction (NeurIPS 2026 · similarity 0.93)
- A^2TG: Adaptive Anisotropic Textured Gaussians for Efficient 3D Scene Representation (ICLR 2026 · similarity 0.91)
- SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction (CVPR 2026 · similarity 0.90)
- Textured Gaussians for Enhanced 3D Scene Appearance Modeling (CVPR 2025 · similarity 0.89)
- Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.88)
- Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene (ICLR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
