CIS565-Fall-2023 · LichengCAO · Jan 16, 2021 · Sep 10, 2021 · Sep 10, 2021 · Sep 18, 2021
diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -62,58 +62,37 @@ set(GLM_ROOT_DIR "external")
 find_package(GLM REQUIRED)
 include_directories(${GLM_INCLUDE_DIRS})
 
-set(headers
-    src/main.h
-    src/image.h
-    src/interactions.h
-    src/intersections.h
-    src/glslUtility.hpp
-    src/pathtrace.h
-    src/scene.h
-    src/sceneStructs.h
-    src/preview.h
-    src/utilities.h
-    )
-
-set(sources
-    src/main.cpp
-    src/stb.cpp
-    src/image.cpp
-    src/glslUtility.cpp
-    src/pathtrace.cu
-    src/scene.cpp
-    src/preview.cpp
-    src/utilities.cpp
-    )
-
-set(imgui
-    imgui/imconfig.h
-    imgui/imgui.cpp
-    imgui/imgui.h
-    imgui/imgui_draw.cpp
-    imgui/imgui_internal.h
-    imgui/imgui_widgets.cpp
-    imgui/imgui_demo.cpp
-    imgui/imgui_impl_glfw.cpp
-    imgui/imgui_impl_glfw.h
-    imgui/imgui_impl_opengl2.cpp
-    imgui/imgui_impl_opengl2.h
-    imgui/imgui_impl_opengl3.cpp
-    imgui/imgui_impl_opengl3.h
-    )
-
-list(SORT headers)
-list(SORT sources)
-list(SORT imgui)
-
-source_group(Headers FILES ${headers})
-source_group(Sources FILES ${sources})
-source_group(imgui FILES ${imgui})
-
-#add_subdirectory(stream_compaction)  # TODO: uncomment if using your stream compaction
-
-cuda_add_executable(${CMAKE_PROJECT_NAME} ${sources} ${headers} ${imgui})
+
+# https://stackoverflow.com/questions/47910256/cmake-how-to-normalize-paths
+file(TO_CMAKE_PATH "${CMAKE_SOURCE_DIR}/scenes" SCENE_PATH)
+add_definitions(-DSCENE_PATH="${SCENE_PATH}/")
+add_definitions(-DROOT_PATH="${CMAKE_SOURCE_DIR}")
+
+file(GLOB SRC_FILES 
+    "${PROJECT_SOURCE_DIR}/src/*.c"
+	"${PROJECT_SOURCE_DIR}/src/*.cpp"
+	"${PROJECT_SOURCE_DIR}/src/*.cc"
+	"${PROJECT_SOURCE_DIR}/src/*.cu"
+    "${PROJECT_SOURCE_DIR}/src/ImGui/*.cpp"
+	)
+
+file(GLOB H_FILES 
+	"${PROJECT_SOURCE_DIR}/src/ImGui/*.h"
+    "${PROJECT_SOURCE_DIR}/src/tinyobj/*.h"
+    "${PROJECT_SOURCE_DIR}/src/*.h"
+    "${PROJECT_SOURCE_DIR}/src/*.hpp"
+    "${PROJECT_SOURCE_DIR}/src/*.cuh"
+)
+list(SORT SRC_FILES)
+list(SORT H_FILES)
+
+#set(SRC_INCLUDE
+#	${PROJECT_SOURCE_DIR}
+#)
+
+cuda_add_executable(${CMAKE_PROJECT_NAME} ${SRC_FILES} ${H_FILES})
+
 target_link_libraries(${CMAKE_PROJECT_NAME}
     ${LIBRARIES}
     #stream_compaction  # TODO: uncomment if using your stream compaction
-    )
+    )
diff --git a/CMakePresets.json b/CMakePresets.json
@@ -0,0 +1,21 @@
+{
+    "version": 2,
+    "configurePresets": [
+        {
+            "name": "windows-default",
+            "displayName": "Windows x64 Debug",
+            "description": "面向具有 Visual Studio 开发环境的 Windows。",
+            "generator": "Ninja",
+            "binaryDir": "${sourceDir}/out/build/${presetName}",
+            "architecture": {
+                "value": "x64",
+                "strategy": "external"
+            },
+            "cacheVariables": {
+                "CMAKE_BUILD_TYPE": "Release",
+                "CMAKE_INSTALL_PREFIX": "${sourceDir}/out/install/${presetName}"
+            },
+            "vendor": { "microsoft.com/VisualStudioSettings/CMake/1.0": { "hostOS": [ "Windows" ] } }
+        }
+    ]
+}
diff --git a/INSTRUCTION.md b/INSTRUCTION.md
@@ -2,7 +2,6 @@ Project 4 CUDA Denoiser - Instructions
 =======================================
 
 This is due **Friday October 20th** at 11:59pm EST.
-
 **Summary:**
 
 In this project, you'll implement a pathtracing denoiser that uses geometry buffers (G-buffers) to guide a smoothing filter.
@@ -85,12 +84,16 @@ Requirements
 
 **Ask in Ed for clarifications.**
 
+
 ## Part 1 - Read!
 
+
 One meta-goal for this project is to help you gain some experience in reading technical papers and implementing their concepts. This is an important skill in graphics software engineering, and will also be helpful for your final projects.
 
+
 For part one, try to skim the paper, and then read through it in depth a couple times: https://jo.dreggn.org/home/2010_atrous.pdf
 
+
 Try to look up anything that you don't understand, and feel free to discuss with your fellow students on Ed. We were also able to locate presentation slides for this paper that may be helpful: https://www.highperformancegraphics.org/previous/www_2010/media/RayTracing_I/HPG2010_RayTracing_I_Dammertz.pdf
 
 This paper is also helpful in that it includes a code sample illustrating some of the math, although not
@@ -164,8 +167,10 @@ Implement methods to store positions and normals more compactly. Two places to s
 
 Be sure to provide performance comparison numbers between optimized and unoptimized implementations.
 
+
 ## Comparing A-trous and Gaussian filtering
 
+
 Dammertz-et-al mention in their section 2.2 that A-trous filtering is a means for approximating gaussian filtering. Implement gaussian filtering and compare with A-trous to see if one method is significantly faster. Also note any visual differences in your results.
 
 ## Shared Memory Filtering
@@ -175,12 +180,16 @@ Filtering techniques can be somewhat memory-expensive - for each pixel, the tech
 Be sure to provide performance comparison numbers between implementations with and without shared memory.
 Also pay attention to how shared memory use impacts the block size for your kernels, and how this may change as the filter width changes.
 
+
 ## Implement Temporal Sampling
 
+
 High-performance raytracers in dynamic applications (like games, or real-time visualization engines) now often use temporal sampling, borrowing and repositioning samples from previous frames so that each frame effectively only computes 1 sample-per-pixel but can denoise from many frames.
 
+
 This will require additional buffers, as well as reprojection code to move samples from where they were in a previous frame to the current frame.
 
+
 Note that our basic pathtracer doesn't do animation, so you will also need to implement some kind of dynamic aspect in your scene - this may be as simple as an automated panning camera, or as complex as translating models.
 
 See https://research.nvidia.com/publication/2017-07_Spatiotemporal-Variance-Guided-Filtering%3A for more details.
@@ -197,9 +206,9 @@ The template of the comment section of your pull request is attached below, you
 
 * [Repo Link](https://link-to-your-repo)
 * (Briefly) Mentions features that you've completed. Especially those bells and whistles you want to highlight
-    * Feature 0
-    * Feature 1
-    * ...
+  * Feature 0
+  * Feature 1
+  * ...
 * Feedback on the project itself, if any.
 
 References

diff --git a/README.md b/README.md
@@ -3,11 +3,66 @@ CUDA Denoiser For CUDA Path Tracer
 
 **University of Pennsylvania, CIS 565: GPU Programming and Architecture, Project 4**
 
-* (TODO) YOUR NAME HERE
-* Tested on: (TODO) Windows 22, i7-2222 @ 2.22GHz 22GB, GTX 222 222MB (Moore 2222 Lab)
+* Licheng CAO
+  * [LinkedIn](https://www.linkedin.com/in/licheng-cao-6a523524b/)
+* Tested on: Windows 10, i7-10870H @ 2.20GHz 32GB, GTX 3060 6009MB
 
-### (TODO: Your README)
+Result
+====
+ * Here are the denoiser results. The outcome is generally deemed acceptable when the sample count is approximately 64.
 
-*DO NOT* leave the README to the last minute! It is a crucial part of the
-project, and we will not be able to grade you without a good README.
+|number of samples| 1 | 4 | 16 | 64 | 128|
+|:--:|:--:|:--:|:--:|:--:|:--:|
+|original|![o1](md_img/o1samp.png)|![o4](md_img/o4samp.png)|![o16](md_img/o16samp.png)|![o64](md_img/o64samp.png)|![o128](md_img/o128samp.png)|
+|denoised|![d1](md_img/d1samp.png)|![d4](md_img/d4samp.png)|![d16](md_img/d16samp.png)|![d64](md_img/d64samp.png)|![d128](md_img/d128samp.png)|
 
+Filter
+===
+* The images below illustrate the storage of g-buffers. As evident in the "1 sample" row, artifacts are present in the storage of normals and positions due to ray jittering for anti-aliasing. To mitigate this, I employ interpolation, combining the output of the previous g-buffer with the current frame's intersection results in my application.
+
+|filter| normal | position | A-trous without weighting |
+|:--:|:--:|:--:|:--:|
+|1 sample|![n](md_img/norm1samp.png)|![p](md_img/pos1samp.png)|![b](md_img/blur1samp.png)|
+|100 sample|![n](md_img/norm.png)|![p](md_img/pos.png)|![b](md_img/blur.png)|
+
+
+Analysis
+===
+## Resolution
+* Based on the table, it's evident that rendering time increases as the resolution is raised. However, the time dedicated to denoising remains relatively consistent across varying resolutions.
+
+|resolution|400x400|600*600|800x800|
+|:---:|:---:|:---:|:---:|
+|origin render time(ms)| 5.43| 8.93 |16.28 |
+|denoise render time(ms)| 6.15| 10.41| 16.85|
+
+## Filter size
+* As anticipated, the render time increases when the filter size is enlarged, as the denoiser has to process more iterations to generate the final result. It's worth noting that neither excessively large nor excessively small filter sizes tend to yield satisfactory results.
+
+|filter size|1|2|3|4|5|
+|:---:|:---:|:---:|:---:|:---:|:---:|
+|render time(ms)|16.18 | 16.46| 18.18| 19.97| 21.77|
+|result| ![f1](md_img/filter1.png)|![f2](md_img/filter2.png) |![f3](md_img/filter3.png) |![f4](md_img/filter4.png) |![f5](md_img/filter5.png) |
+
+## Material
+* Utilizing image color as a filter input can sometimes lead to excessive blurring of the result. Inspired by  [HummaWhite](https://github.com/HummaWhite), I opted to employ the light incident on the surface, rather than the output color, as the filter input. This approach allowed me to apply the texture after denoising, resulting in a significantly improved outcome.
+
+|origin|origin denoise|apply texture after denoise|
+|:---:|:---:|:---:|
+|![o](md_img/o100samp.png)|![od](md_img/col100samp.png)|![c4](md_img/tex100samp.png)|
+
+## Scene
+* The intensity of the lighting can indeed impact the denoiser's output. In the case of the cornelbox scene featuring a large ceiling light, we observed that just 4 samples were sufficient to produce a high-quality result. This result matched or even exceeded the quality of the output from the standard cornelbox scene with 8 samples.
+
+|normal (4 samples)| normal (8 samples)| ceiling light (4 samples)|
+|:---:|:---:|:---:|
+|![c4](md_img/c4samp.png)|![c8](md_img/c8samp.png)|![cl4](md_img/cl4samp.png)|
+
+Third Party
+============
+### Code
+  * [tinyobjloader](https://github.com/tinyobjloader/tinyobjloader)
+  * [imgui](https://github.com/ocornut/imgui)
+  * [stb_image](https://github.com/nothings/stb/blob/master/stb_image.h)
+### Assets
+  * [planet](https://www.turbosquid.com/3d-models/3d-stylized-planet-system-4k-free-1973128)
diff --git a/cmake/CUDAComputesList.cmake b/cmake/CUDAComputesList.cmake
@@ -60,6 +60,8 @@ IF(    CUDA_COMPUTE_20
     OR CUDA_COMPUTE_70
     OR CUDA_COMPUTE_72
     OR CUDA_COMPUTE_75
+    OR CUDA_COMPUTE_80
+    OR CUDA_COMPUTE_86
     )
     SET(FALLBACK OFF)
 ELSE()
@@ -70,8 +72,8 @@ LIST(LENGTH COMPUTES_DETECTED_LIST COMPUTES_LEN)
 IF(${COMPUTES_LEN} EQUAL 0 AND ${FALLBACK})
     MESSAGE(STATUS "You can use -DCOMPUTES_DETECTED_LIST=\"AB;XY\" (semicolon separated list of CUDA Compute versions to enable the specified computes")
     MESSAGE(STATUS "Individual compute versions flags are also available under CMake Advance options")
-    LIST(APPEND COMPUTES_DETECTED_LIST "30" "50" "60" "70")
-    MESSAGE(STATUS "No computes detected. Fall back to 30, 50, 60 70")
+    LIST(APPEND COMPUTES_DETECTED_LIST "30" "50" "60" "70" "80")
+    MESSAGE(STATUS "No computes detected. Fall back to 30, 50, 60, 70, 80")
 ENDIF()
 
 LIST(LENGTH COMPUTES_DETECTED_LIST COMPUTES_LEN)
@@ -90,7 +92,7 @@ MACRO(SET_COMPUTE VERSION)
 ENDMACRO(SET_COMPUTE)
 
 # Iterate over compute versions. Create variables and enable computes if needed
-FOREACH(VER 20 30 32 35 37 50 52 53 60 61 62 70 72 75)
+FOREACH(VER 20 30 32 35 37 50 52 53 60 61 62 70 72 75 80 86)
     OPTION(CUDA_COMPUTE_${VER} "CUDA Compute Capability ${VER}" OFF)
     MARK_AS_ADVANCED(CUDA_COMPUTE_${VER})
     IF(${CUDA_COMPUTE_${VER}})

diff --git a/cmake/FindGLFW.cmake b/cmake/FindGLFW.cmake
@@ -20,66 +20,66 @@
 include(FindPackageHandleStandardArgs)
 
 if (WIN32)
-	# Find include files
-	find_path(
-		GLFW_INCLUDE_DIR
-		NAMES GLFW/glfw3.h
-		PATHS
-		$ENV{PROGRAMFILES}/include
-		${GLFW_ROOT_DIR}/include
-		DOC "The directory where GLFW/glfw.h resides")
+  # Find include files
+  find_path(
+    GLFW_INCLUDE_DIR
+    NAMES GLFW/glfw3.h
+    PATHS
+    $ENV{PROGRAMFILES}/include
+    ${GLFW_ROOT_DIR}/include
+    DOC "The directory where GLFW/glfw.h resides")
 
-	# Use glfw3.lib for static library
-	if (GLFW_USE_STATIC_LIBS)
-		set(GLFW_LIBRARY_NAME glfw3)
-	else()
-		set(GLFW_LIBRARY_NAME glfw3dll)
-	endif()
+  # Use glfw3.lib for static library
+  if (GLFW_USE_STATIC_LIBS)
+    set(GLFW_LIBRARY_NAME glfw3)
+  else()
+    set(GLFW_LIBRARY_NAME glfw3dll)
+  endif()
 
-	# Find library files
-	find_library(
-		GLFW_LIBRARY
-		NAMES ${GLFW_LIBRARY_NAME}
-		PATHS
-		$ENV{PROGRAMFILES}/lib
-		${GLFW_ROOT_DIR}/lib)
+  # Find library files
+  find_library(
+    GLFW_LIBRARY
+    NAMES ${GLFW_LIBRARY_NAME}
+    PATHS
+    $ENV{PROGRAMFILES}/lib
+    ${GLFW_ROOT_DIR}/lib)
 
-	unset(GLFW_LIBRARY_NAME)
+  unset(GLFW_LIBRARY_NAME)
 else()
-	# Find include files
-	find_path(
-		GLFW_INCLUDE_DIR
-		NAMES GLFW/glfw.h
-		PATHS
-		/usr/include
-		/usr/local/include
-		/sw/include
-		/opt/local/include
-		DOC "The directory where GL/glfw.h resides")
+  # Find include files
+  find_path(
+    GLFW_INCLUDE_DIR
+    NAMES GLFW/glfw.h
+    PATHS
+    /usr/include
+    /usr/local/include
+    /sw/include
+    /opt/local/include
+    DOC "The directory where GL/glfw.h resides")
 
-	# Find library files
-	# Try to use static libraries
-	find_library(
-		GLFW_LIBRARY
-		NAMES glfw3
-		PATHS
-		/usr/lib64
-		/usr/lib
-		/usr/local/lib64
-		/usr/local/lib
-		/sw/lib
-		/opt/local/lib
-		${GLFW_ROOT_DIR}/lib
-		DOC "The GLFW library")
+  # Find library files
+  # Try to use static libraries
+  find_library(
+    GLFW_LIBRARY
+    NAMES glfw3
+    PATHS
+    /usr/lib64
+    /usr/lib
+    /usr/local/lib64
+    /usr/local/lib
+    /sw/lib
+    /opt/local/lib
+    ${GLFW_ROOT_DIR}/lib
+    DOC "The GLFW library")
 endif()
 
 # Handle REQUIRD argument, define *_FOUND variable
 find_package_handle_standard_args(GLFW DEFAULT_MSG GLFW_INCLUDE_DIR GLFW_LIBRARY)
 
 # Define GLFW_LIBRARIES and GLFW_INCLUDE_DIRS
 if (GLFW_FOUND)
-	set(GLFW_LIBRARIES ${OPENGL_LIBRARIES} ${GLFW_LIBRARY})
-	set(GLFW_INCLUDE_DIRS ${GLFW_INCLUDE_DIR})
+  set(GLFW_LIBRARIES ${OPENGL_LIBRARIES} ${GLFW_LIBRARY})
+  set(GLFW_INCLUDE_DIRS ${GLFW_INCLUDE_DIR})
 endif()
 
 # Hide some variables