Revise overview and remove inference instructions

README.md

@@ -27,14 +27,14 @@ Accepted at **International Journal of Computer Vision (IJCV), 2026**.
 
 ## Overview
 
-TARGO studies target-driven 6-DoF robotic grasping under visual occlusion. Given a single RGB-D observation and a target object, TARGO-Net uses target shape completion and target-scene feature fusion to predict collision-aware grasp poses that remain robust when the target is partially occluded by clutter.
+Recent advances in predicting 6D grasp poses from a single depth image have led to promising performance in robotic grasping. However, previous grasping models face challenges in cluttered environments where nearby objects impact the target object's grasp. In this paper, we first establish a new benchmark dataset for TARget-driven Grasping under Occlusions, named TARGO. We make the following contributions: 1) We are the first to study the occlusion level of grasping. 2) We set up an evaluation benchmark consisting of large-scale synthetic data and part of real-world data, and we evaluated five grasp models and found that even the current SOTA model suffers when the occlusion level increases, leaving grasping under occlusion still a challenge. 3) We also generate a large-scale training dataset via a scalable pipeline, which can be used to boost the performance of grasping under occlusion and generalized to the real world. 4) We further propose a transformer-based grasping model involving a shape completion module, termed TARGO-Net, which performs most robustly as occlusion increases. Our benchmark dataset can be found at [this https URL](https://targo-benchmark.github.io/).
 
 ## Checkpoints
 
 | File | Description |
 | --- | --- |
 | `checkpoints/targonet.pt` | TARGO-Net grasp prediction checkpoint. |
-| `checkpoints/adapointr.pth` | AdaPoinTr target shape completion checkpoint used by the TARGO-Net inference pipeline. |
+| `checkpoints/adapointr.pth` | AdaPoinTr target shape completion checkpoint used by the TARGO-Net pipeline. |
 
 ## Download
 
@@ -48,27 +48,6 @@ snapshot_download(
 )
 ```
 
-For the cleaned TARGO code, place or link the files as:
-
-```text
-checkpoints/targonet.pt
-checkpoints/adapointr.pth
-```
-
-## Inference
-
-```bash
-python inference_targo.py   --model checkpoints/targonet.pt   --sc_model_path checkpoints/adapointr.pth   --test_root /path/to/processed_vgn/test_set_gaussian_0.002
-```
-
-The processed VGN-format `--test_root` should contain:
-
-```text
-scenes/
-mesh_pose_dict/
-occ_level_dict.json
-```
-
 ## Data
 
 The benchmark/dataset files are not included in this model repository. Please see the project page for code, data, and benchmark details: