liyang/hand-motion-pipeline
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update to 2026-09-17 pipeline snapshot; add weights, L20 assets and recording via Git LFS

Browse Source 
Source: RGB-D -> Dyn-HaMR -> L20 retargeting -> FoundationPose -> reference repair -> SPIDER,
documented in docs/PIPELINE_LATEST.md and docs/SETUP_AND_WEIGHTS.md. Adds FoundationPose and
nvdiffrast upstream snapshots, requirements/pipeline_venv.txt and the FoundationPose weight
manifest/downloader.

Assets (Git LFS): weights/ (WiLoR detector, HandFlow denoiser, UniDepth-L), FoundationPose
checkpoints, HaMeR checkpoint, Dyn-HaMR HMP model and BMC constraints, L20 URDF/meshes, the
20260915_171525 D405 recording and the two box CADs. MANO models are not redistributed
(third_party/hamer/_DATA/data/mano/README.txt). Environments, caches and run outputs excluded.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
liyang
2026-09-17 11:27:46 +08:00
parent 7e4ef6f98b
commit ae28d55f81
761 changed files with 55598 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files
third_party/FoundationPose/bundlesdf/mycuda/common.h
Vendored
+30
View File
@@ -0,0 +1,30 @@
/*
* Copyright (c) 2023, NVIDIA CORPORATION. All rights reserved.
*
* NVIDIA CORPORATION and its licensors retain all intellectual property
* and proprietary rights in and to this software, related documentation
* and any modifications thereto. Any use, reproduction, disclosure or
* distribution of this software and related documentation without an express
* license agreement from NVIDIA CORPORATION is strictly prohibited.
*/
#pragma once
#include <torch/extension.h>
#include <vector>
#define CHECK_CUDA(x) AT_ASSERTM(x.is_cuda(), #x " must be a CUDA tensor")
#define CHECK_CONTIGUOUS(x) AT_ASSERTM(x.is_contiguous(), #x " must be contiguous")
#define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
inline int divCeil(int a, int b)
{
return (a+b-1)/b;
};
at::Tensor sampleRaysUniformOccupiedVoxels(const at::Tensor z_in_out, const at::Tensor z_sampled, at::Tensor z_vals);
at::Tensor postprocessOctreeRayTracing(const at::Tensor ray_index, const at::Tensor depth_in_out, const at::Tensor unique_intersect_ray_ids, const at::Tensor start_poss, const int max_intersections, const int N_rays);
void rayColorToTextureImageCUDA(const at::Tensor &F, const at::Tensor &V, const at::Tensor &hit_locations, const at::Tensor &hit_face_ids, const at::Tensor &uvs_tex, at::Tensor &uvs);