LastKV for scene-level novel-view synthesis, trained on DL3DV with a three-stage progressive-resolution curriculum: 128 × 128 → 256 × 256 → 512 × 512. This repository releases the third-stage checkpoint at 512 × 512. A 24-layer Transformer with hidden width 768, patch size 8, and 184.8M parameters. LastKV shares the final layer's historical KV cache across attention layers. Training uses BF16 autocast; the released model weights are stored in FP32. Stage 1 starts from random initialization. Its perceptual-loss branch continues from the 4,000-pass L2 checkpoint, preserving optimizer, scheduler, and step-counter states. At each resolution transition, only model weights are inherited; the…
Independent publisher
Zefan Cai
ZefanCai
Models in Library2
Datasets in Library0
Models on Hugging Face11
Followers24
Compare the published evidence
This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Reported licenses: mit. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
LastKV for object-centric novel-view synthesis, trained on Objaverse with a three-stage progressive-resolution curriculum: 256 × 256 → 512 × 512 → 1024 × 1024. This repository releases the third-stage checkpoint at 1024 × 1024. A 24-layer Transformer with hidden width 768, patch size 8, and 184.8M parameters. LastKV shares the final layer's historical KV cache across attention layers. Training uses BF16 autocast; the released model weights are stored in FP32. Stage 1 starts from random initialization. At each resolution transition, only model weights are inherited; the optimizer, learning-rate scheduler, and step counters are reset. Checkpoint steps are stage-local forward/backward pass…