Research map / 3D vision / Gaussian splatting
SymGS: Leveraging Reflective Symmetries for 3DGS Compression
Keshav Gupta, Akshat Sanghvi, Shreyas Reddy Palley, Astitva Srivastava, Charu Sharma, Avinash Sharma
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 |
|---|---|---|---|
| finetune the hash-grid MLP during training (ablation) | SymGS (HAC) · Chair, Drums, Room scenes | PSNR (dB): 33.88 -> 34.34 (Chair, L=1) | Improved |
| train anchors from last 5 mirror levels instead of only the last (ablation) | SymGS (HAC) · Chair, Drums, Room scenes | PSNR / size: 34.34 -> 34.60 PSNR (Chair), size 0.80 -> 0.82 | Mixed |
| use coarser accumulator grid gamma_res (ablation) | SymGS · Synthetic-NeRF and Mip-NeRF360 | PSNR and compression | Hurt |
| add SymGS symmetry module to HAC | HAC · Deep Blending | model size (MB): 7.80 -> 2.59 | Improved |
| add SymGS symmetry module to HAC | HAC · Synthetic-NeRF | model size (MB): 1.38 -> 0.95 | Improved |
| add SymGS symmetry module to HAC | HAC · Tanks & Temples | PSNR (dB): 24.14 -> 24.02 | No clear effect |
| add SymGS symmetry module to HAC | HAC · BungeeNeRF | PSNR (dB): 26.44 -> 26.24 | Hurt |
| add SymGS symmetry module to HAC | HAC · Deep Blending | PSNR (dB): 29.85 -> 29.99 | Improved |
Closest papers by meaning
- Fast Feedforward 3D Gaussian Splatting Compression (ICLR 2025 · similarity 0.91)
- Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis (CVPR 2024 · similarity 0.91)
- CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression (ICLR 2025 · similarity 0.90)
- Optimized Minimal 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.90)
- Temporal Smoothness-Aware Rate-Distortion Optimized 4D Gaussian Splatting (NeurIPS 2025 · similarity 0.90)
- Locality-aware Gaussian Compression for Fast and High-quality Rendering (ICLR 2025 · similarity 0.90)
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.
