CAGS delivers 5-20 dB higher PSNR in volumetric video streaming by applying a color-adaptive scheme with vector quantization on 3D Gaussians and server-rendered reference images for client-side color restoration.
year 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
IECD² uses dual instruction and evidence streams with a KL-based contrastive gate to reduce hallucinations and improve grounding in vision-language reasoning tasks like VQA and captioning.
citing papers explorer
-
CAGS: Color-Adaptive Volumetric Video Streaming with Dynamic 3D Gaussian Splatting
CAGS delivers 5-20 dB higher PSNR in volumetric video streaming by applying a color-adaptive scheme with vector quantization on 3D Gaussians and server-rendered reference images for client-side color restoration.
-
Instruction-Evidence Contrastive Dual-Stream Decoding for Grounded Vision-Language Reasoning
IECD² uses dual instruction and evidence streams with a KL-based contrastive gate to reduce hallucinations and improve grounding in vision-language reasoning tasks like VQA and captioning.