| { |
| "method": "LIVE", |
| "dataset": "RE10K", |
| "official_repository": "https://github.com/Junchao-cs/LIVE", |
| "official_commit": "5f0fe658330c64c585874acad3149aa15ba82d1b", |
| "checkpoint_repository": "junchaoh-cs/LIVE-Re10K", |
| "checkpoint_files": [ |
| "live-re10k.ckpt", |
| "vae-kl16.ckpt" |
| ], |
| "checkpoint_global_step": 20500, |
| "weight_source": "raw state_dict; verified no EMA keys", |
| "vae_weight_consistency": "Every VAE inference tensor in final checkpoint equals the separate released VAE tensor exactly", |
| "backbone_checkpoint_tensors": 174, |
| "backbone_checkpoint_elements": 772346944, |
| "backbone_parameters_verified": 772346944, |
| "vae_checkpoint_tensors": 312, |
| "vae_checkpoint_elements": 66456019, |
| "vae_parameters_verified": 66456019, |
| "optimizer_groups": [], |
| "training_lr_stages": "not applicable: inference only", |
| "evaluation_trainable_parameters": 0, |
| "lora_or_adapters": false, |
| "activation_checkpointing": false, |
| "per_gpu_batch_size": 1, |
| "global_parallelism": "independent per-scene workers, 8 GPUs per Berzelius node", |
| "sampler": "official 18-step flow DPM, shift 3, one frame per step", |
| "selector": "native contiguous latest 31 context frames + one generated frame", |
| "context_noise": true, |
| "kv_cache": false, |
| "network_precision": "native fp16 autocast", |
| "vae_precision": "fp32", |
| "vae_scale": 0.2325, |
| "vae_posterior": "native stochastic sample", |
| "common_protocol": { |
| "scene_scope": "final100 (monitor8 smoke subset)", |
| "trajectory": "G0..G199,G199..G0", |
| "source_stride": 1, |
| "observed_frames": 100, |
| "generated_frames": 300, |
| "resolution": [ |
| 256, |
| 256 |
| ], |
| "camera_mapping": "DFoT normalized intrinsics plus raw world-to-camera extrinsics; native window-first normalization", |
| "targets": "shared DFoT-prepared RGB decoded and preprocessed by shared/protocol.py", |
| "model_inputs": "observed RGB only; future camera poses allowed, future RGB excluded", |
| "output": "generated suffix only; shared saver and metric implementation" |
| }, |
| "adaptations": [ |
| "Use exact shared scene manifest, RGB preprocessing and camera timeline", |
| "Pass all 100 observed frames to native autoregressive sampler; preserve its 32-frame context limit", |
| "Disable compilation for portable bounded smoke and evaluation", |
| "Skip unused native metric models; scoring is external and common across methods", |
| "Skip unused FlexAttention mask construction when official SDPA is selected", |
| "Construct deterministic cycle masks on the existing buffer device; normal module device transfer moves them", |
| "Normalize compiled checkpoint key prefixes and strictly load all inference tensors" |
| ], |
| "paper_protocol_difference": "Official paper evaluates skip 2 with one prompt frame and open rollout; common WorldMem evaluation uses skip 1, 100 observations and a closed revisit. Published scores cannot be directly compared.", |
| "required_runtime": { |
| "python": "3.10", |
| "torch": "2.6.0+cu124", |
| "lightning": "2.5.2", |
| "torchmetrics": "1.7.4", |
| "diffusers": "0.34.0", |
| "attention": "torch SDPA efficient_attention (no xformers or FlashAttention dependency)" |
| }, |
| "verification": { |
| "official_clone": "passed", |
| "both_weight_downloads": "passed", |
| "checkpoint_weight_audit": "passed", |
| "python_syntax": "passed", |
| "setup_shell_syntax": "passed", |
| "environment_install": "passed; exact released requirements plus pytorch-lightning 2.5.2 and setuptools 80.9.0", |
| "production_model_preflight": "passed on CPU in dedicated env; strict load of all 486 inference tensors", |
| "real_data_preflight": "passed; first monitor8 scene RGB400x3x256x256, cameras400x16, exact duplicated turnaround and closed endpoint", |
| "native_sampler_boundary_check": "passed; actual 18-step sampler with a constant-flow probe preserves observed latents and matches five explicit sliding camera windows through reversal", |
| "local_gpu_smoke": "root agent schedules after preflight" |
| }, |
| "numerical_failure_policy": "Raise FloatingPointError on sampler/decoder NaN/Inf; never replace with zero frames", |
| "evaluation_case_seed": "1_000_003 * metadata_index + 7 at protocol seed0; NumPy seeds modulo2**32" |
| } |
|
|
