Unverified50% confidenceFactExact time
C3D（2015年）将 2D 卷积扩展为 3D 卷积在时空立方体上学习特征，I3D 通过膨胀预训练 ImageNet 权重实现迁移学习
1
Sources
50%
Confidence
Long-term
Relevance
7/8/2026
First Seen
Sources
Making Any LLM Understand Video: Claude-real-video Technical Deep Dive
hackernewshackernews7/2/2026
Related Claims
VerifiedCompared to NeRF's implicit representation, 3DGS is explicitly differentiable, with training and rendering speeds improved by tens of times.74% similarUnverifiedNVIDIA's solution addresses the challenges of 3D medical image generation through technologies such as latent space compression (Latent Diffusion) and 3D attention mechanisms.71% similarUnverified3D坐标到2D像素坐标的转换流程为：世界坐标系→相机坐标系→裁剪坐标系→NDC→屏幕坐标系70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/215743API
curl https://kongchang.com/api/v1/knowledge/claims/215743MCP
get_claim(id=215743)