I am a rising senior at Basis Independent Silicon Valley. I am passionate about science and engineering. I have published one paper in IEEE International Conference on Visual Communications and Image Processing (2nd author) and had one contribution (single author) adopted by IEEE 3366.3 International Standard project, both related to 3D Gaussian Splatting. I am a competitive fencer and have won 20 national as well as regional medals, including a National Silver medal in Div III Men's Foil. I'm currently ranked #1 in Div II Men's Foil (2025-2026 season). I am a USA Fencing Certified Referee and Junior Coach, and have worked in various tournaments and events with fencers from the world. I am a VEX Robotics team captain and have led the team to won various awards and qualify for US Open. In my spare time, I enjoy playing piano (received State Honors in CM10), reading and travelling. I have been to about 20 countries to explore culture and history.

Email: william-gordon@outlook.com | Cell: 408-603-1884

• Yuke Xing, William Gordon, Qi Yang, Kaifa Yang, Jiarui Wang, Yiling Xu, “3DGS-VBench: A Comprehensive Video Quality Evaluation Benchmark for 3DGS Compression”, to presented in 2025 IEEE International Conference on Visual Communications and Image Processing, December 1-4, 2025. https://ieeexplore.ieee.org/document/11396862.

• William Gordon, "A Proposed 3DGS Dataset for IEEE 3366.3", 3366-12-M0001, 12th IEEE 3366 WG Plenary Meeting, March 19, 2026.

• William Gordon, Yuke Xing, Kaifa Yang, Yiling Xu, “Video Quality Evaluation Benchmark for 3DGS Compression”, invited by Journal of Electrical and Computational Innovations (JECI), ISSN: 3066-1730, to be submitted.

This work presents a high-fidelity Gaussian Splatting (GS) dataset composed of four testing sequences covering different structural details, captured using a high-end digital camera. The reconstructed GS models demonstrate high visual quality and can be used to provide robust benchmarks for evaluating the performance of GS coding and rendering technologies on scenes with various characteristics. This dataset is adopted into IEEE 3366.3 standard common test conditions (CTC).

3D Gaussian Splatting (3DGS) enables real-time novel view synthesis with high visual fidelity, but its significant storage demands limit practical deployment, prompting recent methods to integrate compression modules into 3DGS. However, these 3DGS generative compression techniques introduce unique distortions that lack systematic quality assessment research. To this end, we establish 3DGS-VBench, a large-scale Video Quality Assessment (VQA) dataset and benchmark with 660 compressed 3DGS models and video sequences generated from 11 scenes across 6 representative 3DGS compression algorithms with systematically designed parameter levels. With annotations from 50 participants, we obtain MOS scores with outlier removal and validate dataset reliability. We benchmark 6 3DGS compression algorithms on storage efficiency and visual quality, and evaluate 15 quality assessment metrics across multiple paradigms. Our work enables specialized VQA model training for 3DGS, serving as a catalyst for compression and quality assessment research. The dataset is available upon request.