ByteDance-Seed / ByteDance-Seed/Depth-Anything-3

Why Does Batch Processing Result in Inferior Depth Estimation Quality?

Open
#68 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
6.3k
Forks
702
PR merge metrics
No merged PRs in 30d

Description

Great work! I have a question. When I test the demo on HuggingFace, if I input 10 images at once, the depth results for each image are not as good as when I input them one by one. Why is this happening? The depth estimation quality for each image in batch processing is inferior to processing them individually.

Contributor guide

No contributing guide indexed for this repository

Research direction

No repository file or test is named. Reproduce the HuggingFace demo with one image and with a batch of 10, then inspect the batch-processing and depth-estimation entry points to compare their behavior. Done means identifying the cause of the quality difference and validating a documented or tested correction.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.