Questions about Unprojection in gs_adapter.py
I noticed that the GaussianAdapter module in gs_adapter.py calculates the positions of Gaussian points using:
gs_means_world = origins + directions * gs_depths[..., None]
However, the directions here are normalized in the get_world_rays function via:
directions = directions / directions.norm(dim=-1, keepdim=True)
This step has confused me because, based on the context, the depth value gs_depths should refer to z-depth rather than distance-along-ray. Additionally, in glb.py, unprojection is indeed performed using the unnormalized ray direction with the formula K_inv @ pix * depth (utils/export/glb.py Lines 239-240).
In my tests, I found that the 3DGS rendering effect remains normal when the code is left unchanged. Conversely, removing the ray direction normalization in get_world_rays causes distortion in the rendered images—even after removing the depth offset prediction in gs_dpt, which confirms that the distortion is not compensated for by the offset.
I would greatly appreciate your guidance and insights on this matter!
关于 gs_adapter.py 中反投影逻辑的疑问
我在查看 gs_adapter.py 的 GaussianAdapter 模块时发现，其计算高斯点世界坐标的公式为：
gs_means_world = origins + directions * gs_depths[..., None]
但其中的 directions 在 get_world_rays 函数中已做归一化处理：
directions = directions / directions.norm(dim=-1, keepdim=True)
这一处理让我产生疑惑：结合上下文来看，gs_depths 应为相机 z 轴深度（z-depth），而非射线长度（distance-along-ray）；并且对比 glb.py 中的实现，其反投影确实采用未归一化的射线方向，公式为 K_inv @ pix * depth（对应 utils/export/glb.py 第 239–240 行）。
但我在实际测试中发现：
- 保留原有代码时，3DGS 渲染效果正常；
- 去掉
get_world_rays 中的射线方向归一化后，渲染图像反而出现畸变。
即便去掉 gs_dpt 中的深度偏移（depth offset）预测，畸变依然存在，说明该畸变并非由深度偏移补偿所致。
希望各位大佬不吝赐教！
Questions about Unprojection in
gs_adapter.pyI noticed that the GaussianAdapter module in gs_adapter.py calculates the positions of Gaussian points using:
gs_means_world = origins + directions * gs_depths[..., None]However, the
directionshere are normalized in theget_world_raysfunction via:directions = directions / directions.norm(dim=-1, keepdim=True)This step has confused me because, based on the context, the depth value
gs_depthsshould refer to z-depth rather than distance-along-ray. Additionally, in glb.py, unprojection is indeed performed using the unnormalized ray direction with the formulaK_inv @ pix * depth(utils/export/glb.py Lines 239-240).In my tests, I found that the 3DGS rendering effect remains normal when the code is left unchanged. Conversely, removing the ray direction normalization in
get_world_rayscauses distortion in the rendered images—even after removing the depth offset prediction ings_dpt, which confirms that the distortion is not compensated for by the offset.I would greatly appreciate your guidance and insights on this matter!
关于 gs_adapter.py 中反投影逻辑的疑问
我在查看 gs_adapter.py 的 GaussianAdapter 模块时发现，其计算高斯点世界坐标的公式为：
gs_means_world = origins + directions * gs_depths[..., None]但其中的
directions在get_world_rays函数中已做归一化处理：directions = directions / directions.norm(dim=-1, keepdim=True)这一处理让我产生疑惑：结合上下文来看，
gs_depths应为相机 z 轴深度（z-depth），而非射线长度（distance-along-ray）；并且对比glb.py中的实现，其反投影确实采用未归一化的射线方向，公式为K_inv @ pix * depth（对应 utils/export/glb.py 第 239–240 行）。但我在实际测试中发现：
get_world_rays中的射线方向归一化后，渲染图像反而出现畸变。即便去掉
gs_dpt中的深度偏移（depth offset）预测，畸变依然存在，说明该畸变并非由深度偏移补偿所致。希望各位大佬不吝赐教！