colmap

colmap copied to clipboard

AttributeError: module 'pycolmap' has no attribute 'IncrementalPipeline'

1

**Describe the bug** Within the [custom incremental mapping](https://github.com/colmap/colmap/blob/main/pycolmap/custom_incremental_mapping.py) it uses the pycolmap.IncrementalPipeline() # imports up here ^ # first_start_proc = time.time() with open(image_list_path)as f: my_list = [x.rstrip() for x in...

GeartHub

Could use some guidance on Reconstruction using known camera poses and 3d Pointcloud data

3

Hello, I am trying to use COLMAP for sparse reconstruction of scenes captured via my robot. It appears there is alot of confusion (me included) on what the best way...

shankar-anantak

Do not filter existing, fixed frames

2

Alternative fix for the following issue: https://github.com/colmap/colmap/pull/3158

ahojnnes

Hello, I have noticed that during some reconstructions, there is some scale drifting the more the reconstruction goes for larger set of images. Is there a proper way to handle...

abrahamezzeddine

1

1

**Describe the bug** A clear and concise description of what the bug is. **To Reproduce** Steps to reproduce the behavior: 1. Go to '...' 2. Click on '....' 3. Scroll...

wzq952

Triangulation from known poses fails in 3.10 but works in 3.8

11

I have a problem when I try to reconstruct a sparse model from known camera poses. It works in version 3.8, but when I upgrade to 3.10 it fails. In...

TogachZebra

Support for RTX 50xx Series (sm_120 / CUDA Compute Capability 12.0

8

Hello, I'm trying to compile COLMAP on a system with an NVIDIA RTX 5090 GPU (CUDA Compute Capability 12.0 / sm_120), but the build fails due to unsupported architecture 'compute_native'....

okanklcdev

pose orientation

1

Could you please clarify if the camera pose orientation of Colmap is different from that of Dust3r? And how can we convert the orientation from Dust3r to that of Colmap?

missTL

known intrinsic and extrinsic

3

When performing sparse reconstruction using the known camera intrinsic and extrinsic parameters, no point cloud was obtained at the end. There were no point clouds in the point triangulator stage...

missTL

model_merger from cmd line reduces total number of images and points

3

 I am running model_merger from cmd line with two colmap sparse model inputs. For the two sparse models, they both have 90 images in total. They share 20 images...

YutaoC24