Duplicate from siyan824/slam3r_i2p

Co-authored-by: Siyan Dong <siyan824@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

LICENSE.txt

@@ -0,0 +1,6 @@
+Copyright [2024–present] 
+
+SLAM3R is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 License.  
+
+To view a copy of the CC BY-NC-SA 4.0, visit:  
+https://creativecommons.org/licenses/by-nc-sa/4.0/  

README.md

@@ -0,0 +1,16 @@
+---
+tags:
+- image-to-3d
+- video-to-3d
+
+---
+
+[CVPR 2025] SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos
+
+SLAM3R is a real-time RGB SLAM system that performs dense 3D reconstruction via points regression with feed-forward neural networks.
+
+This repository contains pre-trained weights for the Image-to-Points network, which converts short video clips into dense point clouds with all frames aligned in a unified coordinate system. 
+
+Paper: https://huggingface.co/papers/2412.09401
+
+Code: https://github.com/PKU-VCL-3DV/SLAM3R

config.json

@@ -0,0 +1,29 @@
+{
+  "conf_mode": [
+    "exp",
+    1,
+    Infinity
+  ],
+  "corr_depth": 2,
+  "dec_depth": 12,
+  "dec_embed_dim": 768,
+  "dec_num_heads": 12,
+  "depth_mode": [
+    "exp",
+    -Infinity,
+    Infinity
+  ],
+  "enc_depth": 24,
+  "enc_embed_dim": 1024,
+  "enc_minibatch": 11,
+  "enc_num_heads": 16,
+  "head_type": "linear",
+  "img_size": [
+    224,
+    224
+  ],
+  "mv_dec1": "MultiviewDecoderBlock_max",
+  "mv_dec2": "MultiviewDecoderBlock_max",
+  "output_mode": "pts3d",
+  "pos_embed": "RoPE100"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f58b4a39f9e3641ed2fe19d16a82be956975ec1ecb568899c8852370aa78b8c
+size 2131831108

slam3r_i2p.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c124e11f118e4ba377781f6aacd96465fa1d12d3aada982ae78e7c2cafdf8858
+size 2132077978