Unverified50% confidenceFactExact time
Luce introduces a variational autoencoder (VAE) to compress the multimodal Gaussian cloud into a unified material-aware latent space.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/5/2026
First Seen
Valid until: 12/4/2026
Sources
Related Entities
Related Claims
UnverifiedV模块使用变分自编码器(VAE)将高维像素观测压缩为低维潜向量78% similarUnverifiedLuce proposes a voxelized multimodal Gaussian cloud representation that assigns dedicated Gaussian primitives to each modality (geometry, albedo, metallic-roughness, normals, etc.).70% similarUnverifiedMainstream image and video generation models use VAE for multiple downsampling operations during the encoding stage, typically halving the resolution each time, so the original dimensions must be divisible by 8, 16, or 32 to avoid tensor dimension mismatches.56% similarUnverified3D models generated by Luce can be re-lit and seamlessly integrated into industry-standard rendering pipelines.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/860356API
curl https://kongchang.com/api/v1/knowledge/claims/860356MCP
get_claim(id=860356)