- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper presents a framework for estimating reusable, spatially-varying illumination from an existing 3DGS scene to enable illumination-consistent object insertion. The method generates RGB-D panoramas at multiple locations, reconstructs HDR observations using PanoLight, and estimates a compact set of VPLs through a combination of spatial coverage sampling, HDR importance sampling, and semantic source sampling. The estimated VPLs are further optimized and subsequently used for position-conditioned hybrid rendering.
Critical strengths
-
The proposed pipeline integrates spatial HDR observations, semantic light source priors, mixed VPL sampling, and hybrid rendering. The separation between offline estimation and online rendering is appropriate for real-time applications.
-
Combining spatial coverage sampling, HDR importance sampling, and semantic source sampling is a reasonable strategy for allocating a limited number of VPLs to both dominant direct illumination and distributed environmental light.
Critical weaknesses
-
Although real-time relighting is claimed, the paper does not report any performance statistics such as fps and frame time. Please provide a timing breakdown for cubemap refreshing and hybrid rendering. Additionally, evaluate how the number of VPLs affects the performance.
-
Line 186 mentions "indirect and environment falloff terms" and a "semantic-VPL shadow cubemap," but neither is explained in the main text.
-
Only selecting a dominant VPL as the representative hard shadow caster is oversimplified, which may degrade the realism in the scenes with complex lighting.
-
Line 358 claims that ComGS is based on 3D Gaussians, but ComGS is actually based on 2D Gaussians. Moreover, the objects inserted using ComGS appear to lack cast shadows in the qualitative comparisons, which should be supported in ComGS.
Questions for authors
-
What is the rendering frame rate or frame time?
-
What is the computational overhead of refreshing the local radiance cubemap when the mesh moves?
-
What are the "indirect and environment falloff terms" and "semantic-VPL shadow cubemap" in line 186?
-
In line 273, why is the captured surrounding 3DGS scene required to be modulated using the estimated scene illumination?
-
Why the SynCom dataset provided by ComGS is not included in the evaluation?
-
Why do the objects inserted using ComGS appear to lack cast shadows in the qualitative comparisons?